Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STM
    -0.06
    .UseText
    -0.06
     understands
    -0.06
    URES
    -0.06
    ké
    -0.06
    trigger
    -0.06
    haul
    -0.06
    election
    -0.06
    CHANT
    -0.06
    ools
    -0.06
    POSITIVE LOGITS
     orally
    0.08
    地
    0.07
    可能
    0.07
    /database
    0.07
     serializer
    0.06
     Neb
    0.06
    ambient
    0.06
     votre
    0.06
     questa
    0.06
    特别
    0.06
    Act Density 0.000%

    No Known Activations